73ef4ff3
 Hu Chunming
提交三方库
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
|
//
// Copyright (c) 2009-2011 Artyom Beilis (Tonkikh)
//
// Distributed under the Boost Software License, Version 1.0.
// https://www.boost.org/LICENSE_1_0.txt
/*!
\page conversions Text Conversions
Boost.Locale provides several functions for basic string manipulation:
- \ref boost::locale::to_upper "to_upper": convert a string to upper case
- \ref boost::locale::to_upper "to_lower": convert a string to lower case
- \ref boost::locale::to_title "to_title": convert a string to title case
- \ref boost::locale::fold_case "fold_case": makes a string case-agnostic (see \ref term_case_folding "case folding")
- \ref boost::locale::normalize "normalize": convert equivalent code points to a consistent binary form (\ref term_normalization "normalization")
All these functions receive an \c std::locale object as parameter or use a global locale by default.
Global locale is used in all examples below.
\section conversions_case Case Handing
For example:
\code
std::string grussen = "grüßEN";
std::cout <<"Upper "<< boost::locale::to_upper(grussen) << std::endl
<<"Lower "<< boost::locale::to_lower(grussen) << std::endl
<<"Title "<< boost::locale::to_title(grussen) << std::endl
<<"Fold "<< boost::locale::fold_case(grussen) << std::endl;
\endcode
Would print:
\verbatim
Upper GRÜSSEN
Lower grüßen
Title Grüßen
Fold grüssen
\endverbatim
There are existing functions \c to_upper and \c to_lower in the Boost.StringAlgo library, however the
Boost.Locale functions operate on an entire string instead of performing incorrect character-by-character conversions.
For example:
\code
std::wstring grussen = L"grüßen";
std::wcout << boost::algorithm::to_upper_copy(grussen) << " " << boost::locale::to_upper(grussen) << std::endl;
\endcode
Would give in output:
\verbatim
GRÜßEN GRÜSSEN
\endverbatim
Where a letter "ß" was not converted correctly to double-S in first case because of a limitation of \c std::ctype facet.
This is even more problematic in case of UTF-8 encodings where non US-ASCII are not converted at all.
For example, this code:
\code
std::string grussen = "grüßen";
std::cout << boost::algorithm::to_upper_copy(grussen) << " " << boost::locale::to_upper(grussen) << std::endl;
\endcode
Would modify ASCII characters only
\verbatim
GRüßEN GRÜSSEN
\endverbatim
\section conversions_normalization Unicode Normalization
Unicode normalization is the process of converting strings to a standard form, suitable for text processing and
comparison. For example, character "ü" can be represented by a single code point or a combination of the character "u" and the
diaeresis "¨". Normalization is an important part of Unicode text processing.
Unicode defines four normalization forms. Each specific form is selected by a flag passed
to \ref boost::locale::normalize() "normalize" function:
- NFD - Canonical decomposition - boost::locale::norm_nfd
- NFC - Canonical decomposition followed by canonical composition - boost::locale::norm_nfc or boost::locale::norm_default
- NFKD - Compatibility decomposition - boost::locale::norm_nfkd
- NFKC - Compatibility decomposition followed by canonical composition - boost::locale::norm_nfkc
For more details on normalization forms, read <a href="http://unicode.org/reports/tr15/#Norm_Forms">this report on unicode.org</a>.
\section conversions_notes Notes
- \ref boost::locale::normalize() "normalize" operates only on Unicode-encoded strings, i.e.: UTF-8, UTF-16 and UTF-32 depending on the
character width. So be careful when using non-UTF encodings as they may be treated incorrectly.
- \ref boost::locale::fold_case() "fold_case" is generally a locale-independent operation, but it receives a locale as a parameter to
determine the 8-bit encoding.
- All of these functions can work with an STL string, a NULL terminated string, or a range defined by two pointers. They always
return a newly created STL string.
- The length of the string may change; see the above example.
*/
|
